huangjh-pub/di-fusion
[CVPR'21] [Jittor & Pytorch] DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
This tool helps researchers and engineers quickly create detailed 3D models of environments or objects in real-time. By taking live depth and color video feeds, it produces an accurate 3D map represented by a neural network. It's designed for professionals working in robotics, virtual reality, or 3D scanning.
123 stars. No commits in the last 6 months.
Use this if you need to generate continuous, high-quality 3D reconstructions from streaming camera data as you move through an environment.
Not ideal if you only have static images or prefer offline processing for extremely high precision over real-time performance.
Stars
123
Forks
13
Language
Cuda
License
—
Category
Last pushed
Jul 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/huangjh-pub/di-fusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)